Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Neural Network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 433 records · Page 24

Surface recogniton for cars: A comprehensive approach for neural networks

This paper explores the viability of neural-networkbased classification of ground surface for vehicles. By classifying road surface in near realtime, improvements in vehicle performance (e.g. braking and cornering) may be possible. Classification performance for many combinations of feature encoding and neural network types are compared. The vehicle used here was an An Audi “S3” with a magnetic suspension system on the sport mode. An NI CompactRIO (or cDAQ) module was used to record from a lowing the cDAQ to communicate with the PCB 352C03 one-axis accelerometer. The accelerometer was firmly attached to the windshield of the car. This work focuses on the classification of four road surfaces (asphalt, dirt, concrete, and sand), though larger target sets were also considered. The most accurate method involved a MATLAB feature extraction package with a back-propagation neural network, yielding an overall accuracy of 97%. Lessons learned from this wide exploration of options may extend to other related classification problems.

33 ADVANCED PROPULSION SYSTEMS↗

Neural network–based pore flow field prediction in porous media using super resolution

Direct pore-scale simulations of fluid flow through porous media are computationally expensive to perform for realistic systems. Previous works have demonstrated using the geometry of the microstructure of porous media to predict the velocity fields therein based on neural networks. However, such trained neural networks do not perform well for unseen porous media with a large degree of heterogeneity. In this study we propose that incorporating a coarse velocity field in the input of neural networks is an effective way to improve the prediction performance. The coarse velocity field can be simulated with a low computational cost and provides global information to regularize the ill-posedness of the learning problem, which is usually caused by the use of local geometries due to the computational resource constraints. We show that incorporating the coarse-mesh velocity field significantly improves the prediction accuracy of the fine-mesh velocity field by comparison to the prediction that relies on geometric information alone, especially for the porous medium with a large interior vuggy pore space. We also show the flexibility of training the network in using coarse velocity fields with various resolutions. The results suggest that even using coarse velocity field with a very low resolution, the predictions are still enhanced and close to the ground truths. The feasibility of the method is further demonstrated by testing the trained network on real rocks. This study highlights the merits of incorporating a coarse-mesh velocity field into the input for neural networks, which provides global, physics-based information for the model, thereby improving the model's generalization capability.

42 ENGINEERING↗

A New Neural Network Approach Including First-Guess for Retrieval of Atmospheric Water Vapor, Cloud Liquid Water Path, Surface Temperature and Emissivities Over Land From Satellite Microwave Observations

The analysis of microwave observations over land to determine atmospheric and surface parameters is still limited due to the complexity of the inverse problem. Neural network techniques have already proved successful as the basis of efficient retrieval methods for non-linear cases, however, first-guess estimates, which are used in variational methods to avoid problems of solution non-uniqueness or other forms of solution irregularity, have up to now not been used with neural network methods. In this study, a neural network approach is developed that uses a first-guess. Conceptual bridges are established between the neural network and variational methods. The new neural method retrieves the surface skin temperature, the integrated water vapor content, the cloud liquid water path and the microwave surface emissivities between 19 and 85 GHz over land from SSM/I observations. The retrieval, in parallel, of all these quantities improves the results for consistency reasons. A data base to train the neural network is calculated with a radiative transfer model and a a global collection of coincident surface and atmospheric parameters extracted from the National Center for Environmental Prediction reanalysis, from the International Satellite Cloud Climatology Project data and from microwave emissivity atlases previously calculated. The results of the neural network inversion are very encouraging. The r.m.s. error of the surface temperature retrieval over the globe is 1.3 K in clear sky conditions and 1.6 K in cloudy scenes. Water vapor is retrieved with a r.m.s. error of 3.8 kg/sq m in clear conditions and 4.9 kg/sq m in cloudy situations. The r.m.s. error in cloud liquid water path is 0.08 kg/sq m . The surface emissivities are retrieved with an accuracy of better than 0.008 in clear conditions and 0.010 in cloudy conditions. Microwave land surface temperature retrieval presents a very attractive complement to the infrared estimates in cloudy areas: time record of land surface temperature will be produced.

Aires, F.↗

Bayesian Neural Networks for Uncertainty Analysis of Hydrologic Modeling: A Comparison of Two Schemes

Bayesian Neural Networks (BNNs) have been shown as useful tools to analyze modeling uncertainty of Neural Networks (NNs). This research focuses on the comparison of two BNNs. The first BNNs (BNN-I) use statistical methods to describe the characteristics of different uncertainty sources (input, parameter, and model structure) and integrate these uncertainties into a Markov Chain Monte Carlo (MCMC) framework to estimate total uncertainty. The second BNNs (BNN-II) lump all uncertainties into a single error term (i.e. the residual between model prediction and measurement). In this study, we propose a simple BNN-II, which use Genetic Algorithms (GA) and Bayesian Model Averaging (BMA) to calibrate Neural Networks with different structures (number of hidden units) and combine the predictions from different NNs to derive predictions and uncertainty analysis. We tested these two BNNs in two watersheds for daily and monthly hydrologic simulation. The BMA based BNNs developed in this study outperforms BNN-I in the two watersheds in terms of both accurate prediction and uncertainty estimation. These results show that, given incomplete understanding of the characteristics associated with each uncertainty source, the simple lumped error approach may yield better prediction and uncertainty estimation.

99 GENERAL AND MISCELLANEOUS↗

Deep Neural Network High Spatiotemporal Resolution Precipitation Estimation (Deep-STEP) Using Passive Microwave and Infrared Data

Recent developments in “headline-making” deep neural networks (DNNs), specifically convolutional neural networks (CNNs), along with advancements in computational power, open great opportunities to integrate massive amounts of real-time observations to characterize spatiotemporal structures of surface precipitation. This study aims to develop a CNN algorithm, named Deep Neural Network High Spatiotemporal Resolution Precipitation Estimation (Deep-STEP), that ingests direct satellite passive microwave (PMW) brightness temperatures (Tbs) at emission and scattering frequencies combined with infrared (IR) Tbs from geostationary satellites and surface information to automatically extract geospatial features related to the precipitable clouds. These features allow the end-to-end Deep-STEP algorithm to instantaneously map surface precipitation intensities with a spatial resolution of 4 km. The main advantages of Deep-STEP, as compared to current state-of-the-art techniques, are 1) it learns and estimates complex precipitation systems directly from raw measurements in near–real time, 2) it uses the automatic spatial neighborhood feature extraction approach, and 3) it fuses coarse-resolution PMW footprints with IR images to reliably retrieve surface precipitation at a high spatial resolution. We anticipate our proposed DNN algorithm to be a starting point for more sophisticated and efficient precipitation retrieval systems in terms of accuracy, fine spatial pattern detection skills, and computational costs.

54 ENVIRONMENTAL SCIENCES↗

Application of artificial neural networks in nonlinear analysis of trusses

A method is developed to incorporate neural network model based upon the Backpropagation algorithm for material response into nonlinear elastic truss analysis using the initial stiffness method. Different network configurations are developed to assess the accuracy of neural network modeling of nonlinear material response. In addition to this, a scheme based upon linear interpolation for material data, is also implemented for comparison purposes. It is found that neural network approach can yield very accurate results if used with care. For the type of problems under consideration, it offers a viable alternative to other material modeling methods.

Alam, J.↗

Optical-Correlator Neural Network Based On Neocognitron

Multichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.

Chao, Tien-Hsin↗

Superconducting neural networks with disordered Josephson junction array synaptic networks and leaky integrate-and-fire loop neurons

Fully coupled randomly disordered recurrent superconducting networks with additional open-ended channels for inputs and outputs are considered the basis to introduce a new architecture to neuromorphic computing in this work. Various building blocks of such a network are designed around disordered array synaptic networks using superconducting devices and circuits as an example, while emphasizing that a similar architectural approach may be compatible with several other materials and devices. A multiply coupled (interconnected) disordered array of superconducting loops containing Josephson junctions [equivalent to superconducting quantum interference devices (SQUIDs)] forms the aforementioned collective synaptic network that forms a fully recurrent network together with compatible neuron-like elements and feedback loops, enabling unsupervised learning. This approach aims to take advantage of superior power efficiency, propagation speed, and synchronizability of a small world or a random network over an ordered/regular network. Additionally, it offers a significant factor of increase in scalability. Here, a compatible leaky integrate-and-fire neuron made of superconducting loops with Josephson junctions is presented, along with circuit components for feedback loops as needed to complete the recurrent network. Several of these individual disordered array neural networks can further be coupled together in a similarly disordered way to form a hierarchical architecture of recurrent neural networks that is often suggested as similar to a biological brain.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Membership generation using multilayer neural network

There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.

Kim, Jaeseok↗

Structure–Property Linkage in Alloys Using Graph Neural Network and Explainable Artificial Intelligence

Deep learning tools have recently shown significant potential for accelerating the prediction of microstructure–property linkage in materials. While deep neural networks like convolution neural networks (CNNs) can extract physics information from 3D microstructure images, they often require a large network architecture and substantial training time. In this research, we trained a graph neural network (GNN) using phase field generated microstructures of Ni-Al alloys to predict the evolution of mechanical properties. We found that a single GNN is capable of accurately predicting the strengthening of Ni-Al alloys with microstructures of varying sizes and dimensions, which cannot otherwise be done with a CNN. Additionally, GNN requires significantly less GPU utilization than CNN and offers more interpretable explanation of predictions using saliency analysis as features are manually defined in the graph. We also utilize explainable artificial intelligence tool Bayesian Inference to determine the coefficients in the power law equation that governs coarsening of precipitates. Overall, our work demonstrates the ability of the GNN to accurately and efficiently extract relevant information from material microstructures without having restrictions on microstructure size or dimension and offers an interpretable explanation.

Chemistry↗

Effects of input gradient regularization on neural networks time-series forecasting of thermal power systems

This study proposes using neural networks, specifically gated recurrent unit (GRU), long-short-term memory (LSTM), and transformer networks, to improve control strategies in a 450 MW coal-fired power plant. However, neural networks face issues of becoming overly dependent on just a few variables to make predictions, which negatively impacts control decisions that rely on the model to determine the value of all manipulated variables. The paper introduces regularization techniques, including noise injection and input gradient regularization, during the training phase. Here, the work presents novel contributions in adapting neural networks to control industrial systems and applying regularization techniques from computer vision to industrial process control. Results demonstrate the effectiveness of input gradient regularization in reducing model dependence on subsets of variables, emphasizing the balance between fidelity and controllability. Further exploration is recommended, including the development of recurrent transformers, closed-loop control testing, and a sensitivity analysis on computer models to provide further insight.

20 FOSSIL-FUELED POWER PLANTS↗

Two-Scale Neural Networks for Partial Differential Equations with Small Parameters

We propose a two-scale neural network method for solving partial differential equations (PDEs) with small parameters using physics-informed neural networks (PINNs). We directly incorporate the small parameters into the architecture of neural networks. The proposed method enables solving PDEs with small parameters in a simple fashion, without adding Fourier features or other computationally taxing searches of truncation parameters. Various numerical examples demonstrate reasonable accuracy in capturing features of large derivatives in the solutions caused by small parameters.

97 MATHEMATICS AND COMPUTING↗

Neural Network and Regression Methods Demonstrated in the Design Optimization of a Subsonic Aircraft

The neural network and regression methods of NASA Glenn Research Center s COMETBOARDS design optimization testbed were used to generate approximate analysis and design models for a subsonic aircraft operating at Mach 0.85 cruise speed. The analytical model is defined by nine design variables: wing aspect ratio, engine thrust, wing area, sweep angle, chord-thickness ratio, turbine temperature, pressure ratio, bypass ratio, fan pressure; and eight response parameters: weight, landing velocity, takeoff and landing field lengths, approach thrust, overall efficiency, and compressor pressure and temperature. The variables were adjusted to optimally balance the engines to the airframe. The solution strategy included a sensitivity model and the soft analysis model. Researchers generated the sensitivity model by training the approximators to predict an optimum design. The trained neural network predicted all response variables, within 5-percent error. This was reduced to 1 percent by the regression method. The soft analysis model was developed to replace aircraft analysis as the reanalyzer in design optimization. Soft models have been generated for a neural network method, a regression method, and a hybrid method obtained by combining the approximators. The performance of the models is graphed for aircraft weight versus thrust as well as for wing area and turbine temperature. The regression method followed the analytical solution with little error. The neural network exhibited 5-percent maximum error over all parameters. Performance of the hybrid method was intermediate in comparison to the individual approximators. Error in the response variable is smaller than that shown in the figure because of a distortion scale factor. The overall performance of the approximators was considered to be satisfactory because aircraft analysis with NASA Langley Research Center s FLOPS (Flight Optimization System) code is a synthesis of diverse disciplines: weight estimation, aerodynamic analysis, engine cycle analysis, propulsion data interpolation, mission performance, airfield length for landing and takeoff, noise footprint, and others.

Hopkins, Dale A.↗

Energy Efficient Stochastic-Based Deep Spiking Neural Networks for Sparse Datasets

With large deep neural networks (DNNs) neces- sary to solve complex and data-intensive problems, energy efficiency is a key bottleneck for effectively deploying DL in the real world. Deep spiking NNs have gained much research at- tention recently due to the interest in building biological neural networks and the availability of neuromorphic platforms, which can be orders of magnitude more energy efficient compared to CPUs and GPUs. Although spiking NNs have proven to be an efficient technique for solving many machine learning and computer vision problems, to the best of our knowledge, this is the first attempt to adapt spiking NNs to sparse datasets. In this paper, we study the behaviour of spiking NNs in handling NLP datasets and the sparsity in their data representation. Then, we propose a novel framework for spiking NN using the concept of stochastic computing. Specifically, instead of generating spike trains with firing rates proportional to the intensity of each value in the feature set separately, the whole feature set is treated as a distribution function and a stochastic spiking train that follow this distribution is generated. This framework reduces the connectivity between NN layers from O(N) to O(logN). Also, it encodes input data differently and make suitable to handle sparse datasets. Finally, the framework achieves high energy efficiency since it uses Integrate and Fire neurons same as conventional spiking NNs. The results show that our proposed stochastic-based SNN achieves nearly the same accuracy as the original DNN on MNIST dataset, and it has better performance than state- of-the-art SNN. Besides that stochastic-based SNN is energy efficient, where the fully connected DNN, the conventional SNN, and the data normalized SNN consume 38.24, 1.83, and 1.85 -times more energy than the stochastic-based SNN, respectively. For sparse datasets, including IMDb and In-House clinical datasets, stochastic-based SNN achieves performance comparable to that of the conventional DNN. However, the conventional spiking NN has a significant decline in classification accuracy.

Alawad, Mohammed↗

Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators

We developed two neural-network (NN)-based algorithms (fully-connected neural network (Fc-NN) and recurrent neural network (RNN)) to perform pulse shape discrimination (PSD) and identification of piled-up pulses produced by organic scintillators, upon interaction with neutrons and gamma rays. We tested the algorithms on measured and verification sets of data and compared their classification performances to standard approaches. At a high acquisition count rate (100,000 counts per second, cps), in the presence of a gamma-to-neutron ratio of approximately 400–1, the proposed NN-based algorithm achieves a fraction of misclassified neutron, gamma, and piled-up pulses of approximately 1%, 1.8%, and 0.6%, respectively. Compared to the traditional approach, it exhibits 3×, 14×, and 11× improved (lower) miscalculation rates for neutron, gamma, and piled-up pulses, respectively. Here, we also demonstrate the capability of NN-based algorithms of successfully recovering and identifying neutron and gamma ray compositions from piled-up pulses in challenging, high pulse count rate conditions.

42 ENGINEERING↗

Multispectral image fusion using neural networks

A prototype system is being developed to demonstrate the use of neural network hardware to fuse multispectral imagery. This system consists of a neural network IC on a motherboard, a circuit card assembly, and a set of software routines hosted by a PC-class computer. Research in support of this consists of neural network simulations fusing 4 to 7 bands of Landsat imagery and fusing (separately) multiple bands of synthetic imagery. The simulations, results, and a description of the prototype system are presented.

Kagel, J. H.↗

Feed Forward Neural Network and Optimal Control Problem with Control and State Constraints

A feed forward neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints. The paper extends adaptive critic neural network architecture proposed by [5] to the optimal control problems with control and state constraints. The optimal control problem is transcribed into a nonlinear programming problem which is implemented with adaptive critic neural network. The proposed simulation method is illustrated by the optimal control problem of nitrogen transformation cycle model. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.

99 GENERAL AND MISCELLANEOUS↗

The role of simulation in the design of a neural network chip

An iterative, simulation-based design procedure for a neural network chip is introduced. For this design procedure, the goal is to produce a chip layout for a neural network in which the weights are determined by transistor gate width-to-length ratios. In a given iteration, the current layout is simulated using the circuit simulator SPICE, and layout adjustments are made based on conventional gradient-decent methods. After the iteration converges, the chip is fabricated. Monte Carlo analysis is used to predict the effect of statistical fabrication process variations on the overall performance of the neural network chip.

Desai, Utpal↗